English
Related papers

Related papers: Adaptive Monte Carlo via Bandit Allocation

200 papers

We provide a general methodology for unbiased estimation for intractable stochastic models. We consider situations where the target distribution can be written as an appropriate limit of distributions, and where conventional approaches…

Methodology · Statistics 2014-12-01 Sergios Agapiou , Gareth O. Roberts , Sebastian J. Vollmer

Practitioners of Bayesian statistics have long depended on Markov chain Monte Carlo (MCMC) to obtain samples from intractable posterior distributions. Unfortunately, MCMC algorithms are typically serial, and do not scale to the large…

Machine Learning · Statistics 2015-06-11 Maxim Rabinovich , Elaine Angelino , Michael I. Jordan

While multilevel Monte Carlo (MLMC) methods for the numerical approximation of partial differential equations with random coefficients enjoy great popularity, combinations with spatial adaptivity seem to be rare. We present an adaptive MLMC…

Numerical Analysis · Mathematics 2017-12-20 Ralf Kornhuber , Evgenia Youett

We study Pareto optimality in multi-objective multi-armed bandit by providing a formulation of adversarial multi-objective multi-armed bandit and defining its Pareto regrets that can be applied to both stochastic and adversarial settings.…

Machine Learning · Computer Science 2023-06-01 Mengfan Xu , Diego Klabjan

In this paper, we study the problem of estimating uniformly well the mean values of several distributions given a finite budget of samples. If the variance of the distributions were known, one could design an optimal sampling strategy by…

Machine Learning · Computer Science 2015-07-17 Alexandra Carpentier , Alessandro Lazaric , Mohammad Ghavamzadeh , Rémi Munos , Peter Auer , András Antos

We investigate the adversarial bandit problem with multiple plays under semi-bandit feedback. We introduce a highly efficient algorithm that asymptotically achieves the performance of the best switching $m$-arm strategy with minimax optimal…

Machine Learning · Computer Science 2019-12-02 N. Mert Vural , Hakan Gokcesu , Kaan Gokcesu , Suleyman S. Kozat

Real-world distributed systems and networks are often unreliable and subject to random failures of its components. Such a stochastic behavior affects adversely the complexity of optimization tasks performed routinely upon such systems, in…

Artificial Intelligence · Computer Science 2012-12-12 Milos Hauskrecht , Tomas Singliar

In this paper, we introduce a new approach to constructing unbiased estimators when computing expectations of path functionals associated with stochastic differential equations (SDEs). Our randomization idea is closely related to…

Computational Finance · Quantitative Finance 2012-07-11 Chang-han Rhee , Peter W. Glynn

We study stochastic gradient descent for solving conditional stochastic optimization problems, in which an objective to be minimized is given by a parametric nested expectation with an outer expectation taken with respect to one random…

Numerical Analysis · Mathematics 2023-04-28 Takashi Goda , Wataru Kitade

The increasing size of data sets has lead to variable selection in regression becoming increasingly important. Bayesian approaches are attractive since they allow uncertainty about the choice of variables to be formally included in the…

Computation · Statistics 2014-12-30 Jim Griffin , Krzysztof Latuszynski , Mark Steel

This paper considers the problem of maximizing an expectation function over a finite set, or finite-arm bandit problem. We first propose a naive stochastic bandit algorithm for obtaining a probably approximately correct (PAC) solution to…

Optimization and Control · Mathematics 2022-06-16 Marie Billaud-Friess , Arthur Macherey , Anthony Nouy , Clémentine Prieur

Constructing unbiased estimators from Markov chain Monte Carlo (MCMC) outputs is a difficult problem that has recently received a lot of attention in the statistics and machine learning communities. However, the current unbiased MCMC…

Computation · Statistics 2022-12-27 Guanyang Wang , Tianze Wang

Performing numerical integration when the integrand itself cannot be evaluated point-wise is a challenging task that arises in statistical analysis, notably in Bayesian inference for models with intractable likelihood functions. Markov…

Computation · Statistics 2020-06-17 Lawrence Middleton , George Deligiannidis , Arnaud Doucet , Pierre E. Jacob

Stochastic optimization in learning and inference often relies on Markov chain Monte Carlo (MCMC) to approximate gradients when exact computation is intractable. However, finite-time MCMC estimators are biased, and reducing this bias…

Statistics Theory · Mathematics 2026-02-02 Antoine Godichon-Baggioni , Gabriel Lang , Sylvain Le Corff , Julien Stoehr , Sobihan Surendran

In this paper, we aim to compute numerical approximation integral by using an adaptive Monte Carlo algorithm. We propose a stratified sampling algorithm based on an iterative method which splits the strata following some quantities called…

Numerical Analysis · Mathematics 2015-07-22 Toni Sayah

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic…

Machine Learning · Computer Science 2019-03-29 Anupam Gupta , Tomer Koren , Kunal Talwar

It has been known for a long time that stratification is one possible strategy to obtain higher convergence rates for the Monte Carlo estimation of integrals over the hyper-cube $[0, 1]^s$ of dimension $s$. However, stratified estimators…

Computation · Statistics 2025-01-10 Nicolas Chopin , Hejin Wang , Mathieu Gerber

We consider the problem of estimating expectations with respect to a target distribution with an unknown normalizing constant, and where even the unnormalized target needs to be approximated at finite resolution. This setting is ubiquitous…

Numerical Analysis · Mathematics 2023-03-23 Kody J. H. Law , Neil Walton , Shangda Yang , Ajay Jasra

Multifidelity Monte Carlo methods rely on a hierarchy of possibly less accurate but statistically correlated simplified or reduced models, in order to accelerate the estimation of statistics of high-fidelity models without compromising the…

Numerical Analysis · Mathematics 2020-10-29 Alessio Quaglino , Simone Pezzuto , Rolf Krause

We study reward maximisation in a wide class of structured stochastic multi-armed bandit problems, where the mean rewards of arms satisfy some given structural constraints, e.g. linear, unimodal, sparse, etc. Our aim is to develop methods…

Machine Learning · Statistics 2020-07-03 Rémy Degenne , Han Shao , Wouter M. Koolen